Prepositions in applications: A survey and introduction to the special issue
Computational Linguistics
Rich bitext projection features for parse reranking
EACL '09 Proceedings of the 12th Conference of the European Chapter of the Association for Computational Linguistics
Quantifying constructional productivity with unseen slot members
CALC '09 Proceedings of the Workshop on Computational Approaches to Linguistic Creativity
Sentence diagram generation using dependency parsing
ACLstudent '09 Proceedings of the ACL-IJCNLP 2009 Student Research Workshop
Using web-scale N-grams to improve base NP parsing performance
COLING '10 Proceedings of the 23rd International Conference on Computational Linguistics
Web-scale features for full-scale parsing
HLT '11 Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies - Volume 1
Parsing noun phrases in the penn treebank
Computational Linguistics
Parse correction with specialized models for difficult attachment types
EMNLP '11 Proceedings of the Conference on Empirical Methods in Natural Language Processing
Simple semi-supervised learning for prepositional phrase attachment
IWPT '11 Proceedings of the 12th International Conference on Parsing Technologies
Word sense and semantic relations in noun compounds
ACM Transactions on Speech and Language Processing (TSLP) - Special issue on multiword expressions: From theory to practice and use, part 2
Hi-index | 0.00 |
Work on prepositional phrase (PP) attachment resolution generally assumes that there is an oracle that provides the two hypothesized structures that we want to choose between. The information that there are two possible attachment sites and the information about the lexical heads of those phrases is usually extracted from gold-standard parse trees. We show that the performance of reattachment methods is higher with such an oracle than without. Because oracles are not available in NLP applications, this indicates that the current evaluation methodology for PP attachment does not produce realistic performance numbers. We argue that PP attachment should not be evaluated in isolation, but instead as an integral component of a parsing system, without using information from the gold-standard oracle.